ClaudeBot/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-17 20:31:47 +02:00
Code Issues Packages Projects Releases Wiki Activity
11,028 Commits 790 Branches 7,480 Tags

Default Branch

master

972d2313bc · ci : add missing evict-old-files (#29041) · Updated 2026-09-17 19:05:40 +02:00
 ZIP  TAR.GZ

Branches

allozaur/ui/types-cleanup

e5278550ff · ui : type-safe API types, fetch helpers and download-ready models store plumbing · Updated 2026-09-16 13:12:04 +02:00
28
3
 ZIP  TAR.GZ
gg/llama-context-report-graph-inputs

f8bbd553cc · llama-graph : name the unnamed graph input tensors · Updated 2026-09-15 18:37:09 +02:00
42
4
 ZIP  TAR.GZ
0cc4m/fp8-scaled-mm

1b434fb686 · vulkan: add fp8 and scaled matmul support · Updated 2026-09-15 17:19:00 +02:00
216
7
 ZIP  TAR.GZ
gg/ggml-alloc-refactor-meta

d2ebf492e0 · cont : fix cur_buf_size init after flushing a buffer · Updated 2026-09-15 14:30:02 +02:00
42
2
 ZIP  TAR.GZ
rpc_tensor

04eec7a336 · move graph_uids to rpc_dispatcher · Updated 2026-09-15 14:26:37 +02:00
42
3
 ZIP  TAR.GZ
qwen4exp-hc-fuse

26276bc99e · qwen4exp: add hc ops · Updated 2026-09-14 15:32:26 +02:00
73
1
 ZIP  TAR.GZ
alde/refactor-json-schema-qwen3

5746cc7b8c · cont : clean up grammar a bit · Updated 2026-09-12 23:14:54 +02:00
94
2
 ZIP  TAR.GZ
alde/refactor-json-schema

3a3f76f2e8 · cont : rename common_schema to common_chat_schema · Updated 2026-09-12 20:23:12 +02:00
97
27
 ZIP  TAR.GZ
xsn/download_flock

3c0c071cbf · simplify · Updated 2026-09-12 15:35:10 +02:00
99
2
 ZIP  TAR.GZ
gg/rpc-tensor

a70de036ff · rpc : add rdma_cm setup path for iWARP · Updated 2026-09-12 14:50:02 +02:00
98
3
 ZIP  TAR.GZ
xsn/server_refactor_router_subproc

8d79143a4d · Revert "tests: serialize the router tests that download the same model" · Updated 2026-09-11 23:31:38 +02:00
111
6
 ZIP  TAR.GZ
aman/qwen-sparse

41a4ad00dd · CUDA: enable sparse fa for qwen4 · Updated 2026-09-11 17:06:46 +02:00
210
1
 ZIP  TAR.GZ
aman/fix-offload-bug

3c6409920f · ggml: skip 0-sized ids tensor when offloading selected experts · Updated 2026-09-11 09:39:39 +02:00
210
1
 ZIP  TAR.GZ
xsn/mtmd_video_id

e5d72461ae · mtmd: propagate video ID to bitmap · Updated 2026-09-08 11:54:16 +02:00
170
1
 ZIP  TAR.GZ
cross-profiler

89f2417d62 · Apply batched suggestions from code review · Updated 2026-09-08 10:43:25 +02:00
191
2
 ZIP  TAR.GZ
xsn/log_jsonl_fit

7275941a06 · fit: add demo LOG_JSON · Updated 2026-09-07 23:46:16 +02:00
179
2
 ZIP  TAR.GZ
pr-24546-recreated

f01a75498e · CUDA: pick MMQ tile size against ncols_opt set on the host side · Updated 2026-09-07 16:39:17 +02:00
179
2
 ZIP  TAR.GZ
revert-mmq-moe-ncols

2265b7fa41 · Revert "CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 (#24546)" · Updated 2026-09-07 16:19:36 +02:00
180
1
 ZIP  TAR.GZ
xsn/models_fix_hang

eee2fa9c79 · server: keep a queued model out of the victim pool until its waiters leave · Updated 2026-09-07 13:39:02 +02:00
191
2
 ZIP  TAR.GZ
xsn/train_fix1

3f6205741d · llama: properly handle KV on training · Updated 2026-09-07 01:00:51 +02:00
198
1
 ZIP  TAR.GZ